Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dd7d58ed16399cfa5d2b8736620c5ab172c74234527ff26abbabe19a4c0d52c
+oid sha256:f3224f773e5d633f5e9159195dea76a8e552d8e77af6e059cabfe5104d19e565
 size 5327744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74c0ba58562c00c83423d90ef3e99e5d189d18fdc328276736b9527dacc7721e
+oid sha256:2c0a1073d44970e8fbf92dad2a87f61f746cb9095299a72fecdcd61e2fed3abe
 size 2857722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ba0e3ce140969765456ab28381d510e1c0af709a91c5c00aa793a7d6c8c7309
+oid sha256:9eed11b0ebf5a249b18de757685fc6a35e62c6bcdc6b8c81a82108bffe96e390
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
+oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0003733239311009945,
+  "epoch": 0.00041480436788999387,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,13 @@
       "eval_samples_per_second": 37.261,
       "eval_steps_per_second": 18.632,
       "step": 9
+    },
+    {
+      "epoch": 0.00041480436788999387,
+      "grad_norm": 4.040714740753174,
+      "learning_rate": 0.0002,
+      "loss": 7.0398,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -116,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 28129102921728.0,
+  "total_flos": 32375005249536.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null